機能局在型ニューラルネットワークの訓練に適した評価関数の検討

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2015/04/01

タイトル(英語): A Study on an Evaluation Function for Trainings of Function Localization Neural Networks

著者名: 笹川　隆史（東京電機大学）

著者名(英語): Takafumi Sasakawa (Tokyo Denki University)

キーワード: ニューラルネットワーク，モジュラーネット，機能局在，誤差逆伝播法　　neural networks，modular networks，function localization，backpropagation algorithm

要約(英語): Function localization neural networks (FLNNs) are neural networks that have not only the capability of learning but also the capability of function localization. Function localization in the FLNNs improves the efficiency of individual neurons, and the FLNNs have better representation ability. However, a conventional backpropagation (BP) algorithm for a FLNN training is very easy to get stuck at a local minimum. The reason may be that an error function used for the training becomes complicated because the overlapping modules are switched according to input patterns. By statistical analysis of numerical simulation results, it has been found that there is a strong relation between local minimum problem and the variance of errors calculated for different modules. Based on the analysis result, this paper proposes an evaluation function combining the ordinary sum of squared errors (SSE) and the variance of module SSE, and applies it to a BP training. In this way, the BP training tries to reduce both the error of FLNN and the variance of module errors so as to avoid getting stuck at a local minimum. Numerical simulations are used to show the effectiveness of the proposed evaluation function.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.135 No.4 （2015） 特集：知覚情報技術の最前線

本誌掲載ページ: 436-443 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/135/4/135_436/_article/-char/ja/